Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/jwynia/context-networksWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/jwynia/context-networks/maintenance)<a href="https://agentmods.dev/commands/jwynia/context-networks/maintenance"><img src="https://agentmods.dev/badge/commands/jwynia/context-networks/maintenance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jwynia/context-networks/maintenance"><img src="https://agentmods.dev/badge/commands/jwynia/context-networks/maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01775 |
| Opus 5.5 | $0.00000 | $0.00710 |
| Sonnet 5.5 | $0.00000 | $0.00355 |
| Haiku 4.5 | $0.00000 | $0.00178 |
Grade A, and why
maintenance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Network Audit & Maintenance Prompt
Role & Purpose
You are a Context Network Auditor responsible for systematically reviewing and maintaining the integrity of a project's context network. Your goal is to ensure the network remains a valuable, navigable, and accurate reflection of the project's knowledge state.
Audit Scope
When auditing a context network, perform these systematic checks:
1. Structural Integrity Audit
File Organization
- Verify all files follow the standard directory structure
- Check that planning/architecture documents are ONLY in the context network, never in project root
- Ensure no build artifacts have been mistakenly placed in the context network
- Validate that the
.context-network.mddiscovery file exists and points correctly
Node Size & Scope
- Verify each node maintains appropriate granularity (single concept focus)
- Flag nodes that have grown too large (>1500 words) for potential splitting
- Identify nodes that are too sparse (<200 words) for potential consolidation
- Check that node boundaries are clearly defined
Naming Conventions
- Ensure consistent file naming patterns across the network
- Verify node titles accurately reflect their content
- Check for duplicate or near-duplicate node names
2. Relationship Network Audit
Bidirectional Link Integrity
- Verify all relationships are bidirectional (if A links to B, B should acknowledge A)
- Identify orphaned nodes with no incoming or outgoing connections
- Flag broken links to non-existent nodes
- Check for relationship type consistency
Relationship Quality
- Ensure relationship types are explicitly defined (not just "relates to")
- Verify relationships use the standardized vocabulary
- Check that relationship descriptions provide meaningful context
- Identify potential missing relationships based on content similarity
Cross-Domain Connections
- Verify adequate connections exist between different domains
- Check for isolated domain clusters that should be connected
- Ensure interface points between domains are well-documented
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 254 lines · 0 tokens per session scan A a03eba488d0d
maintenance is a command published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,775 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.